Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Beyond the annotations (which already declare readOnly/idempotent/non-destructive/closed-world), the description adds real behavioral context: fixed 25-item page size, newest-first ordering, cursor continuation via nextCursor->beforeId, immutability of receipts, and that payloads carry locators/hashes rather than source text. This meaningfully exceeds the annotation coverage.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three tightly-packed sentences with zero filler, front-loading the core action and scope before pagination and recovery guidance. Every clause carries information useful to the caller.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 5-parameter tool with nested objects and no output schema, the description adequately covers purpose, pagination, content nature and follow-up tool, but leaves the two revision-pinning parameters (contextRevision, expectedReadRevision) unexplained, which are central to calling it correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is only 20% (just projectId is documented), and 4 of 5 parameters are required. The description only clarifies beforeId (as the cursor carrier); sourceKey, contextRevision, and expectedReadRevision — the nested revision-pinning objects — receive no explanation in either the schema or the description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description gives a specific verb+resource ('Read ... page receipts') with scope ('25', 'current source session', 'newest first') and clarifies what a receipt is (locators/hashes, not source text). It is clearly distinguishable from siblings like read_original_page, though it does not name those siblings explicitly.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It states the driving scenario ('Recover exact page revisions after interruption') and routes the agent to the follow-up tool ('replay them through read_original_page'). There is no explicit 'do not use when' exclusion, but the recovery context is clear enough to select the tool.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.